Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Attribution Quality Evaluation on HotpotQA
Loading...
4.1
Log-Prob Drop
Random
0.376
25.513
50.65
75.787
Jun 24, 2025
Log-Prob Drop
BERTScore
Updated 1mo ago
Evaluation Results
Method
Method
Links
Log-Prob Drop
BERTScore
Random
Top-k=k = 1, Backbone=...
2025.06
4.1
78.2
Random
Top-k=k = 3, Backbone=...
2025.06
10.7
70.4
Random
Top-k=k = 5, Backbone=...
2025.06
18.4
64.9
ContextCite
Top-k=k = 1, Backbone=...
2025.06
54.1
49
SHAP
Top-k=k = 1, Backbone=...
2025.06
62.8
50.4
CAMAB
Top-k=k = 1, Backbone=...
2025.06
65
48.6
ContextCite
Top-k=k = 3, Backbone=...
2025.06
80.2
39.3
ContextCite
Top-k=k = 5, Backbone=...
2025.06
86.7
37
SHAP
Top-k=k = 3, Backbone=...
2025.06
87.9
39.4
CAMAB
Top-k=k = 3, Backbone=...
2025.06
91.7
37.2
SHAP
Top-k=k = 5, Backbone=...
2025.06
94.8
37.5
CAMAB
Top-k=k = 5, Backbone=...
2025.06
97.2
35.5
Feedback
Search any
task
Search any
task